paper-with-me

홈 › Papers

Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images

2026-03-22 · Jiatong Xia, Lingqiao Liu arxiv

We introduce a novel, training-free system for reconstructing, understanding, and rendering 3D indoor scenes from a sparse set of unposed RGB images. Unlike traditional radiance field approaches that require dense views and per-scene optimization, our pipeline achieves high-fidelity results without any training or pose preprocessing. The system integrates three key innovations: (1) A robust point cloud reconstruction module that filters unreliable geometry using a warping-based anomaly removal strategy; (2) A warping-guided 2D-to-3D instance lifting mechanism that propagates 2D segmentation masks into a consistent, instance-aware 3D representation; and (3) A novel rendering approach that projects the point cloud into new views and refines the renderings with a 3D-aware diffusion model. Our method leverages the generative power of diffusion to compensate for missing geometry and enhances realism, especially under sparse input conditions. We further demonstrate that object-level scene editing such as instance removal can be naturally supported in our pipeline by modifying only the point cloud, enabling the synthesis of consistent, edited views without retraining. Our results establish a new direction for efficient, editable 3D content generation without relying on scene-specific optimization. Project page: https://jiatongxia.github.io/TID3R/

📄 PDF Abstract BibTeX arXiv:2603.21166

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splatting

2025-11-10 · Chenpeng Su, Wenhua Wu, Chensheng Peng, Tianchen Deng 외 arxiv

Urban scene reconstruction is critical for autonomous driving, enabling structured 3D representations for data synthesis and closed-loop testing. Supervised approaches rely on costly human annotations and lack scalabilit…

Autonomous Driving

FreeOcc: Training-free Panoptic Occupancy Prediction via Foundation Models

2026-03-06 · Andrew Caunes, Thierry Chateau, Vincent Fremont arxiv

Semantic and panoptic occupancy prediction for road scene analysis provides a dense 3D representation of the ego vehicle's surroundings. Current camera-only approaches typically rely on costly dense 3D supervision or req…

Scene Understanding

FreeGen: Feed-Forward Reconstruction-Generation Co-Training for Free-Viewpoint Driving Scene Synthesis

2025-12-04 · Shijie Chen, Peixi Peng arxiv

Closed-loop simulation and scalable pre-training for autonomous driving require synthesizing free-viewpoint driving scenes. However, existing datasets and generative pipelines rarely provide consistent off-trajectory obs…

Autonomous Driving

FurnSet: Exploiting Repeats for 3D Scene Reconstruction

2026-04-22 · Paul Dobre, Xin Wang, Hongzhou Yang arxiv

Single-view 3D scene reconstruction involves inferring both object geometry and spatial layout. Existing methods typically reconstruct objects independently or rely on implicit scene context, failing to exploit the repea…

Point Clouds

BUOL: A Bottom-Up Framework with Occupancy-aware Lifting for Panoptic 3D Scene Reconstruction From A Single Image

2023-06-01 · CVPR 2023 1 · Tao Chu, Pan Zhang, Qiong Liu, Jiaqi Wang

Understanding and modeling the 3D scene from a single image is a practical problem. A recent advance proposes a panoptic 3D scene reconstruction task that performs both 3D reconstruction and 3D panoptic segmentation from…

3D Panoptic Segmentation3D Reconstruction3D Scene ReconstructionPanoptic Segmentation